pruned(text): 预期参数#0(从零开始)是张量；得到清单（['烤蚂蚁是哥伦比亚的一种流行小吃']）

Question

这是使用 EMLo 获取嵌入的代码。

import tensorflow_hub as hub

import tensorflow as tf

elmo = hub.Module("https://tfhub.dev/google/elmo/2")

x = ["Roasted ants are a popular snack in Columbia"]


embeddings = elmo(x, signature="default", as_dict=True)["elmo"] # To Extract ELMo features 

embeddings.shape

我收到这种类型的错误，type error : pruned(text): expected argument #0(zero-based) to be a Tensor; got list (['Roasted ants are a popular snack in Columbia'])。

Answer 1

这段代码在 colab 中运行良好Tensorflow 2.7，

import tensorflow_hub as hub

import tensorflow as tf

elmo = hub.Module("https://tfhub.dev/google/elmo/2")

x = ["Roasted ants are a popular snack in Columbia"]


embeddings = elmo(x, signature="default", as_dict=True)["elmo"] # To Extract ELMo features 

embeddings.shape

输出：

TensorShape([Dimension(1), Dimension(8), Dimension(1024)])

让我们知道正在使用哪个tensorflow版本environment来重现此错误。